Skip to content

GitLab

Commit a75c64d8 authored by Lysandre's avatar Lysandre
Browse files

Black 20 release

parent e78c1103
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 719 additions and 618 deletions
src/transformers/configuration_pegasus.py
View file @ a75c64d8
......@@ -92,8 +92,8 @@ expected_alpha = {
@add_start_docstrings_to_callable(BART_CONFIG_ARGS_DOC)
class PegasusConfig(BartConfig):
r"""
:class:`~transformers.PegasusConfig` is the configuration class to store the configuration of a
`PegasusModel`.
:class:`~transformers.PegasusConfig` is the configuration class to store the configuration of a
`PegasusModel`.
"""
model_type = "pegasus"
# The implementation of the config object is in BartConfig
src/transformers/configuration_reformer.py
View file @ a75c64d8
......@@ -29,105 +29,105 @@ REFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = {
class ReformerConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.ReformerModel`.
It is used to instantiate an Reformer model according to the specified arguments, defining the model
architecture.
This is the configuration class to store the configuration of a :class:`~transformers.ReformerModel`.
It is used to instantiate an Reformer model according to the specified arguments, defining the model
architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Args:
attention_head_size (:obj:`int`, optional, defaults to 64):
Dimensionality of the projected key, query and value vectors
attn_layers (:obj:`list(str)`, optional, defaults to ["local", "lsh", "local", "lsh", "local", "lsh"]):
List of attention layer types in ascending order. It can be chosen between a
LSHSelfAttention layer ("lsh") and a LocalSelfAttention layer ("local").
For more information on LSHSelfAttention layer, see `LSH Self Attention <reformer.html#lsh-self-attention>`__ .
For more information on LocalSelfAttention layer, see `Local Self Attention <reformer.html#local-sensitive-hashing-self-attention>`__ .
axial_pos_embds (:obj:`bool`, optional, defaults to True):
If `True` use axial position embeddings. For more information on how axial position embeddings work, see `Axial Position Encodings <reformer.html#axial-positional-encodings>`__
axial_norm_std (:obj:`float`, optional, defaluts to 1.0):
The standard deviation of the normal_initializer for initializing the weight matrices of the axial positional encodings.
axial_pos_shape (:obj:`list(int)`, optional, defaults to `[64, 64]`):
The position dims of the axial position encodings.
During training the product of the position dims has to equal the sequence length.
For more information on how axial position embeddings work, see `Axial Position Encodings <reformer.html#axial-positional-encodings>`__.
axial_pos_embds_dim (:obj:`list(int)`, optional, defaults to `[64, 192]`):
The embedding dims of the axial position encodings.
The sum of the embedding dims has to equal the hidden size.
For more information on how axial position embeddings work, see `Axial Position Encodings <reformer.html#axial-positional-encodings>`__.
chunk_size_lm_head (:obj:`int`, optional, defaults to 0):
The chunk size of the final language model feed forward head layer.
A chunk size of 0 means that the feed forward layer is not chunked.
A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time.
For more information on feed forward chunking, see `How does Feed Forward Chunking work? <../glossary.html#feed-forward-chunking>`__ .
eos_token_id (:obj:`int`, optional, defaults to 2):
The token id for the <EOS> token.
feed_forward_size (:obj:`int`, optional, defaults to 512):
Dimensionality of the "feed_forward" (i.e., feed-forward) layer in the residual attention block.
hash_seed (:obj:`int`, optional, defaults to `None`):
Seed that can be used to make local sensitive hashing in LSHSelfAttention deterministic. This should only be set for testing purposed. For evaluation and training purposes `hash_seed` should be set to `None` to ensure fully random rotations in local sensitive hashing scheme.
hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "relu"):
The non-linear activation function (function or string) in the feed forward layer in the residual attention block.
If string, "gelu", "relu", "swish", "gelu_new" and "gelu_fast" are supported.
hidden_dropout_prob (:obj:`float`, optional, defaults to 0.05):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
hidden_size (:obj:`int`, optional, defaults to 256):
Dimensionality of the output hidden states of the residual attention blocks.
initializer_range (:obj:`float`, optional, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
is_decoder (:obj:`bool`, optional, defaults to False):
If `is_decoder` is True, a causal mask is used in addition to `attention_mask`.
When using the Reformer for causal language modeling, `is_decoder` is set to `True`.
layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
The epsilon used by the layer normalization layers.
local_chunk_length (:obj:`int`, optional, defaults to 64):
Length of chunk which attends to itself in LocalSelfAttention. Chunking reduces memory complexity from sequence length x sequence length (self attention) to chunk length x chunk length x sequence length / chunk length (chunked self attention).
local_num_chunks_before (:obj:`int`, optional, defaults to 1):
Number of previous neighbouring chunks to attend to in LocalSelfAttention layer to itself.
local_num_chunks_after (:obj:`int`, optional, defaults to 0):
Number of following neighbouring chunks to attend to in LocalSelfAttention layer in addition to itself.
local_attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout ratio for the attention probabilities in LocalSelfAttention.
lsh_attn_chunk_length (:obj:`int`, optional, defaults to 64):
Length of chunk which attends to itself in LSHSelfAttention. Chunking reduces memory complexity from sequence length x sequence length (self attention) to chunk length x chunk length x sequence length / chunk length (chunked self attention).
lsh_num_chunks_before (:obj:`int`, optional, defaults to 1):
Number of previous neighbouring chunks to attend to in LSHSelfAttention layer to itself.
lsh_num_chunks_after (:obj:`int`, optional, defaults to 0):
Number of following neighbouring chunks to attend to in LSHSelfAttention layer to itself.
lsh_attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout ratio for the attention probabilities in LSHSelfAttention.
max_position_embeddings (:obj:`int`, optional, defaults to 4096):
The maximum sequence length that this model might ever be used with.
Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
num_attention_heads (:obj:`int`, optional, defaults to 12):
Number of attention heads for each attention layer in the Transformer encoder.
num_buckets (:obj:`int` or :obj:`list(int)`, optional, defaults to `None`):
Number of buckets, the key query vectors can be "hashed into" using the locality sensitive hashing scheme. Each query key vector is hashed into a hash in `1, ..., num_buckets`.
The number of buckets can also be factorized into a list for improved memory complexity. In this case, each query key vector is hashed into a hash in `1-1, 1-2, ..., num_buckets[0]-1, ..., num_buckets[0]-num_buckets[1]` if `num_buckets` is factorized into two factors.
The number of buckets (or the product the factors) should approximately equal sequence length / lsh_chunk_length. If `num_buckets` is set to `None`, a good value for `num_buckets` is calculated on the fly.
num_hashes (:obj:`int`, optional, defaults to 1):
Number of hashing rounds (e.g. number of random rotations) in Local Sensitive Hashing scheme.
The higher `num_hashes`, the more accurate the `LSHSelfAttention` becomes, but also the more memory and time intensive the hashing becomes.
pad_token_id (:obj:`int`, optional, defaults to 0):
The token id for the <PAD> token.
vocab_size (:obj:`int`, optional, defaults to 320):
Vocabulary size of the Reformer model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.ReformerModel`.
Args:
attention_head_size (:obj:`int`, optional, defaults to 64):
Dimensionality of the projected key, query and value vectors
attn_layers (:obj:`list(str)`, optional, defaults to ["local", "lsh", "local", "lsh", "local", "lsh"]):
List of attention layer types in ascending order. It can be chosen between a
LSHSelfAttention layer ("lsh") and a LocalSelfAttention layer ("local").
For more information on LSHSelfAttention layer, see `LSH Self Attention <reformer.html#lsh-self-attention>`__ .
For more information on LocalSelfAttention layer, see `Local Self Attention <reformer.html#local-sensitive-hashing-self-attention>`__ .
axial_pos_embds (:obj:`bool`, optional, defaults to True):
If `True` use axial position embeddings. For more information on how axial position embeddings work, see `Axial Position Encodings <reformer.html#axial-positional-encodings>`__
axial_norm_std (:obj:`float`, optional, defaluts to 1.0):
The standard deviation of the normal_initializer for initializing the weight matrices of the axial positional encodings.
axial_pos_shape (:obj:`list(int)`, optional, defaults to `[64, 64]`):
The position dims of the axial position encodings.
During training the product of the position dims has to equal the sequence length.
For more information on how axial position embeddings work, see `Axial Position Encodings <reformer.html#axial-positional-encodings>`__.
axial_pos_embds_dim (:obj:`list(int)`, optional, defaults to `[64, 192]`):
The embedding dims of the axial position encodings.
The sum of the embedding dims has to equal the hidden size.
For more information on how axial position embeddings work, see `Axial Position Encodings <reformer.html#axial-positional-encodings>`__.
chunk_size_lm_head (:obj:`int`, optional, defaults to 0):
The chunk size of the final language model feed forward head layer.
A chunk size of 0 means that the feed forward layer is not chunked.
A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time.
For more information on feed forward chunking, see `How does Feed Forward Chunking work? <../glossary.html#feed-forward-chunking>`__ .
eos_token_id (:obj:`int`, optional, defaults to 2):
The token id for the <EOS> token.
feed_forward_size (:obj:`int`, optional, defaults to 512):
Dimensionality of the "feed_forward" (i.e., feed-forward) layer in the residual attention block.
hash_seed (:obj:`int`, optional, defaults to `None`):
Seed that can be used to make local sensitive hashing in LSHSelfAttention deterministic. This should only be set for testing purposed. For evaluation and training purposes `hash_seed` should be set to `None` to ensure fully random rotations in local sensitive hashing scheme.
hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "relu"):
The non-linear activation function (function or string) in the feed forward layer in the residual attention block.
If string, "gelu", "relu", "swish", "gelu_new" and "gelu_fast" are supported.
hidden_dropout_prob (:obj:`float`, optional, defaults to 0.05):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
hidden_size (:obj:`int`, optional, defaults to 256):
Dimensionality of the output hidden states of the residual attention blocks.
initializer_range (:obj:`float`, optional, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
is_decoder (:obj:`bool`, optional, defaults to False):
If `is_decoder` is True, a causal mask is used in addition to `attention_mask`.
When using the Reformer for causal language modeling, `is_decoder` is set to `True`.
layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
The epsilon used by the layer normalization layers.
local_chunk_length (:obj:`int`, optional, defaults to 64):
Length of chunk which attends to itself in LocalSelfAttention. Chunking reduces memory complexity from sequence length x sequence length (self attention) to chunk length x chunk length x sequence length / chunk length (chunked self attention).
local_num_chunks_before (:obj:`int`, optional, defaults to 1):
Number of previous neighbouring chunks to attend to in LocalSelfAttention layer to itself.
local_num_chunks_after (:obj:`int`, optional, defaults to 0):
Number of following neighbouring chunks to attend to in LocalSelfAttention layer in addition to itself.
local_attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout ratio for the attention probabilities in LocalSelfAttention.
lsh_attn_chunk_length (:obj:`int`, optional, defaults to 64):
Length of chunk which attends to itself in LSHSelfAttention. Chunking reduces memory complexity from sequence length x sequence length (self attention) to chunk length x chunk length x sequence length / chunk length (chunked self attention).
lsh_num_chunks_before (:obj:`int`, optional, defaults to 1):
Number of previous neighbouring chunks to attend to in LSHSelfAttention layer to itself.
lsh_num_chunks_after (:obj:`int`, optional, defaults to 0):
Number of following neighbouring chunks to attend to in LSHSelfAttention layer to itself.
lsh_attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout ratio for the attention probabilities in LSHSelfAttention.
max_position_embeddings (:obj:`int`, optional, defaults to 4096):
The maximum sequence length that this model might ever be used with.
Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
num_attention_heads (:obj:`int`, optional, defaults to 12):
Number of attention heads for each attention layer in the Transformer encoder.
num_buckets (:obj:`int` or :obj:`list(int)`, optional, defaults to `None`):
Number of buckets, the key query vectors can be "hashed into" using the locality sensitive hashing scheme. Each query key vector is hashed into a hash in `1, ..., num_buckets`.
The number of buckets can also be factorized into a list for improved memory complexity. In this case, each query key vector is hashed into a hash in `1-1, 1-2, ..., num_buckets[0]-1, ..., num_buckets[0]-num_buckets[1]` if `num_buckets` is factorized into two factors.
The number of buckets (or the product the factors) should approximately equal sequence length / lsh_chunk_length. If `num_buckets` is set to `None`, a good value for `num_buckets` is calculated on the fly.
num_hashes (:obj:`int`, optional, defaults to 1):
Number of hashing rounds (e.g. number of random rotations) in Local Sensitive Hashing scheme.
The higher `num_hashes`, the more accurate the `LSHSelfAttention` becomes, but also the more memory and time intensive the hashing becomes.
pad_token_id (:obj:`int`, optional, defaults to 0):
The token id for the <PAD> token.
vocab_size (:obj:`int`, optional, defaults to 320):
Vocabulary size of the Reformer model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.ReformerModel`.
Example::
Example::
>>> from transformers import ReformerModel, ReformerConfig
>>> from transformers import ReformerModel, ReformerConfig
>>> # Initializing a Reformer configuration
>>> configuration = ReformerConfig()
>>> # Initializing a Reformer configuration
>>> configuration = ReformerConfig()
>>> # Initializing a Reformer model
>>> model = ReformerModel(configuration)
>>> # Initializing a Reformer model
>>> model = ReformerModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "reformer"
......
src/transformers/configuration_retribert.py
View file @ a75c64d8
......@@ -28,47 +28,47 @@ RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
class RetriBertConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.RetriBertModel`.
It is used to instantiate a RetriBertModel model according to the specified arguments, defining the model
architecture.
This is the configuration class to store the configuration of a :class:`~transformers.RetriBertModel`.
It is used to instantiate a RetriBertModel model according to the specified arguments, defining the model
architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Args:
vocab_size (:obj:`int`, optional, defaults to 30522):
Vocabulary size of the BERT model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.BertModel`.
hidden_size (:obj:`int`, optional, defaults to 768):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (:obj:`int`, optional, defaults to 12):
Number of hidden layers in the Transformer encoder.
num_attention_heads (:obj:`int`, optional, defaults to 12):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (:obj:`int`, optional, defaults to 3072):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "gelu"):
The non-linear activation function (function or string) in the encoder and pooler.
If string, "gelu", "relu", "swish" and "gelu_new" are supported.
hidden_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout ratio for the attention probabilities.
max_position_embeddings (:obj:`int`, optional, defaults to 512):
The maximum sequence length that this model might ever be used with.
Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
type_vocab_size (:obj:`int`, optional, defaults to 2):
The vocabulary size of the `token_type_ids` passed into :class:`~transformers.BertModel`.
initializer_range (:obj:`float`, optional, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
The epsilon used by the layer normalization layers.
share_encoders (:obj:`bool`, optional, defaults to True):
Whether to use the same Bert-type encoder for the queries and document
projection_dim (:obj:`int`, optional, defaults to 128):
Final dimension of the query and document representation after projection
Args:
vocab_size (:obj:`int`, optional, defaults to 30522):
Vocabulary size of the BERT model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.BertModel`.
hidden_size (:obj:`int`, optional, defaults to 768):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (:obj:`int`, optional, defaults to 12):
Number of hidden layers in the Transformer encoder.
num_attention_heads (:obj:`int`, optional, defaults to 12):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (:obj:`int`, optional, defaults to 3072):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
hidden_act (:obj:`str` or :obj:`function`, optional, defaults to "gelu"):
The non-linear activation function (function or string) in the encoder and pooler.
If string, "gelu", "relu", "swish" and "gelu_new" are supported.
hidden_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (:obj:`float`, optional, defaults to 0.1):
The dropout ratio for the attention probabilities.
max_position_embeddings (:obj:`int`, optional, defaults to 512):
The maximum sequence length that this model might ever be used with.
Typically set this to something large just in case (e.g., 512 or 1024 or 2048).
type_vocab_size (:obj:`int`, optional, defaults to 2):
The vocabulary size of the `token_type_ids` passed into :class:`~transformers.BertModel`.
initializer_range (:obj:`float`, optional, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
The epsilon used by the layer normalization layers.
share_encoders (:obj:`bool`, optional, defaults to True):
Whether to use the same Bert-type encoder for the queries and document
projection_dim (:obj:`int`, optional, defaults to 128):
Final dimension of the query and document representation after projection
"""
model_type = "retribert"
......
src/transformers/configuration_roberta.py
View file @ a75c64d8
......@@ -33,34 +33,33 @@ ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
class RobertaConfig(BertConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.RobertaModel`.
It is used to instantiate an RoBERTa model according to the specified arguments, defining the model
architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
the BERT `bert-base-uncased <https://huggingface.co/bert-base-uncased>`__ architecture.
This is the configuration class to store the configuration of a :class:`~transformers.RobertaModel`.
It is used to instantiate an RoBERTa model according to the specified arguments, defining the model
architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
the BERT `bert-base-uncased <https://huggingface.co/bert-base-uncased>`__ architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
The :class:`~transformers.RobertaConfig` class directly inherits :class:`~transformers.BertConfig`.
It reuses the same defaults. Please check the parent class for more information.
The :class:`~transformers.RobertaConfig` class directly inherits :class:`~transformers.BertConfig`.
It reuses the same defaults. Please check the parent class for more information.
Example::
Example::
>>> from transformers import RobertaConfig, RobertaModel
>>> from transformers import RobertaConfig, RobertaModel
>>> # Initializing a RoBERTa configuration
>>> configuration = RobertaConfig()
>>> # Initializing a RoBERTa configuration
>>> configuration = RobertaConfig()
>>> # Initializing a model from the configuration
>>> model = RobertaModel(configuration)
>>> # Initializing a model from the configuration
>>> model = RobertaModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "roberta"
def __init__(self, pad_token_id=1, bos_token_id=0, eos_token_id=2, **kwargs):
"""Constructs RobertaConfig.
"""
"""Constructs RobertaConfig."""
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
src/transformers/configuration_t5.py
View file @ a75c64d8
......@@ -31,33 +31,33 @@ T5_PRETRAINED_CONFIG_ARCHIVE_MAP = {
class T5Config(PretrainedConfig):
r"""
:class:`~transformers.T5Config` is the configuration class to store the configuration of a
`T5Model`.
:class:`~transformers.T5Config` is the configuration class to store the configuration of a
`T5Model`.
Arguments:
vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `T5Model`.
d_model: Size of the encoder layers and the pooler layer. `d_model` can also accesed via the property `hidden_size`.
num_layers: Number of hidden layers in the Transformer encoder. `num_layers` can also be accessed via the property `num_hidden_layers`.
d_kv: Size of the key, query, value projections per attention head. `d_kv` has to be equal to `d_model // num_heads`.
d_ff: Size of the intermediate feed forward layer in each `T5Block`.
num_heads: Number of attention heads for each attention layer in
the Transformer encoder. `num_heads` can also be accessed via the property `num_attention_heads`.
intermediate_size: The size of the "intermediate" (i.e., feed-forward)
layer in the Transformer encoder.
hidden_act: The non-linear activation function (function or string) in the
encoder and pooler. If string, "gelu", "relu", "swish" and "gelu_new" are supported.
hidden_dropout_prob: The dropout probabilitiy for all fully connected
layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob: The dropout ratio for the attention
probabilities.
n_positions: The maximum sequence length that this model might
ever be used with. Typically set this to something large just in case
(e.g., 512 or 1024 or 2048). `n_positions` can also be accessed via the property `max_position_embeddings`.
type_vocab_size: The vocabulary size of the `token_type_ids` passed into
`T5Model`.
initializer_factor: A factor for initializing all weight matrices (should be kept to 1.0, used for initialization testing).
layer_norm_eps: The epsilon used by LayerNorm.
Arguments:
vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `T5Model`.
d_model: Size of the encoder layers and the pooler layer. `d_model` can also accesed via the property `hidden_size`.
num_layers: Number of hidden layers in the Transformer encoder. `num_layers` can also be accessed via the property `num_hidden_layers`.
d_kv: Size of the key, query, value projections per attention head. `d_kv` has to be equal to `d_model // num_heads`.
d_ff: Size of the intermediate feed forward layer in each `T5Block`.
num_heads: Number of attention heads for each attention layer in
the Transformer encoder. `num_heads` can also be accessed via the property `num_attention_heads`.
intermediate_size: The size of the "intermediate" (i.e., feed-forward)
layer in the Transformer encoder.
hidden_act: The non-linear activation function (function or string) in the
encoder and pooler. If string, "gelu", "relu", "swish" and "gelu_new" are supported.
hidden_dropout_prob: The dropout probabilitiy for all fully connected
layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob: The dropout ratio for the attention
probabilities.
n_positions: The maximum sequence length that this model might
ever be used with. Typically set this to something large just in case
(e.g., 512 or 1024 or 2048). `n_positions` can also be accessed via the property `max_position_embeddings`.
type_vocab_size: The vocabulary size of the `token_type_ids` passed into
`T5Model`.
initializer_factor: A factor for initializing all weight matrices (should be kept to 1.0, used for initialization testing).
layer_norm_eps: The epsilon used by LayerNorm.
"""
model_type = "t5"
......@@ -80,7 +80,10 @@ class T5Config(PretrainedConfig):
**kwargs
):
super().__init__(
pad_token_id=pad_token_id, eos_token_id=eos_token_id, is_encoder_decoder=is_encoder_decoder, **kwargs,
pad_token_id=pad_token_id,
eos_token_id=eos_token_id,
is_encoder_decoder=is_encoder_decoder,
**kwargs,
)
self.vocab_size = vocab_size
self.n_positions = n_positions
......
src/transformers/configuration_transfo_xl.py
View file @ a75c64d8
......@@ -31,84 +31,84 @@ TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = {
class TransfoXLConfig(PretrainedConfig):
"""
This is the configuration class to store the configuration of a :class:`~transformers.TransfoXLModel`.
It is used to instantiate a Transformer XL model according to the specified arguments, defining the model
architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
the `Transformer XL <https://huggingface.co/transfo-xl-wt103>`__ architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Args:
vocab_size (:obj:`int`, optional, defaults to 267735):
Vocabulary size of the Transformer XL model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.TransfoXLModel`.
cutoffs (:obj:`List[int]`, optional, defaults to :obj:`[20000, 40000, 200000]`):
Cutoffs for the adaptive softmax
d_model (:obj:`int`, optional, defaults to 1024):
Dimensionality of the model's hidden states.
d_embed (:obj:`int`, optional, defaults to 1024):
Dimensionality of the embeddings
n_head (:obj:`int`, optional, defaults to 16):
Number of attention heads for each attention layer in the Transformer encoder.
d_head (:obj:`int`, optional, defaults to 64):
Dimensionality of the model's heads.
d_inner (:obj:`int`, optional, defaults to 4096):
Inner dimension in FF
div_val (:obj:`int`, optional, defaults to 4):
Divident value for adapative input and softmax
pre_lnorm (:obj:`boolean`, optional, defaults to :obj:`False`):
Apply LayerNorm to the input instead of the output
n_layer (:obj:`int`, optional, defaults to 18):
Number of hidden layers in the Transformer encoder.
tgt_len (:obj:`int`, optional, defaults to 128):
Number of tokens to predict
ext_len (:obj:`int`, optional, defaults to 0):
Length of the extended context
mem_len (:obj:`int`, optional, defaults to 1600):
Length of the retained previous heads
clamp_len (:obj:`int`, optional, defaults to 1000):
use the same pos embeddings after clamp_len
same_length (:obj:`boolean`, optional, defaults to :obj:`True`):
Use the same attn length for all tokens
proj_share_all_but_first (:obj:`boolean`, optional, defaults to :obj:`True`):
True to share all but first projs, False not to share.
attn_type (:obj:`int`, optional, defaults to 0):
Attention type. 0 for Transformer-XL, 1 for Shaw et al, 2 for Vaswani et al, 3 for Al Rfou et al.
sample_softmax (:obj:`int`, optional, defaults to -1):
number of samples in sampled softmax
adaptive (:obj:`boolean`, optional, defaults to :obj:`True`):
use adaptive softmax
dropout (:obj:`float`, optional, defaults to 0.1):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
dropatt (:obj:`float`, optional, defaults to 0):
The dropout ratio for the attention probabilities.
untie_r (:obj:`boolean`, optional, defaults to :obj:`True`):
Untie relative position biases
init (:obj:`string`, optional, defaults to `normal`):
Parameter initializer to use
init_range (:obj:`float`, optional, defaults to 0.01):
Parameters initialized by U(-init_range, init_range).
proj_init_std (:obj:`float`, optional, defaults to 0.01):
Parameters initialized by N(0, init_std)
init_std (:obj:`float`, optional, defaults to 0.02):
Parameters initialized by N(0, init_std)
layer_norm_epsilon (:obj:`float`, optional, defaults to 1e-5):
The epsilon to use in the layer normalization layers
Example::
>>> from transformers import TransfoXLConfig, TransfoXLModel
>>> # Initializing a Transformer XL configuration
>>> configuration = TransfoXLConfig()
>>> # Initializing a model from the configuration
>>> model = TransfoXLModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
This is the configuration class to store the configuration of a :class:`~transformers.TransfoXLModel`.
It is used to instantiate a Transformer XL model according to the specified arguments, defining the model
architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
the `Transformer XL <https://huggingface.co/transfo-xl-wt103>`__ architecture.
Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used
to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig`
for more information.
Args:
vocab_size (:obj:`int`, optional, defaults to 267735):
Vocabulary size of the Transformer XL model. Defines the different tokens that
can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.TransfoXLModel`.
cutoffs (:obj:`List[int]`, optional, defaults to :obj:`[20000, 40000, 200000]`):
Cutoffs for the adaptive softmax
d_model (:obj:`int`, optional, defaults to 1024):
Dimensionality of the model's hidden states.
d_embed (:obj:`int`, optional, defaults to 1024):
Dimensionality of the embeddings
n_head (:obj:`int`, optional, defaults to 16):
Number of attention heads for each attention layer in the Transformer encoder.
d_head (:obj:`int`, optional, defaults to 64):
Dimensionality of the model's heads.
d_inner (:obj:`int`, optional, defaults to 4096):
Inner dimension in FF
div_val (:obj:`int`, optional, defaults to 4):
Divident value for adapative input and softmax
pre_lnorm (:obj:`boolean`, optional, defaults to :obj:`False`):
Apply LayerNorm to the input instead of the output
n_layer (:obj:`int`, optional, defaults to 18):
Number of hidden layers in the Transformer encoder.
tgt_len (:obj:`int`, optional, defaults to 128):
Number of tokens to predict
ext_len (:obj:`int`, optional, defaults to 0):
Length of the extended context
mem_len (:obj:`int`, optional, defaults to 1600):
Length of the retained previous heads
clamp_len (:obj:`int`, optional, defaults to 1000):
use the same pos embeddings after clamp_len
same_length (:obj:`boolean`, optional, defaults to :obj:`True`):
Use the same attn length for all tokens
proj_share_all_but_first (:obj:`boolean`, optional, defaults to :obj:`True`):
True to share all but first projs, False not to share.
attn_type (:obj:`int`, optional, defaults to 0):
Attention type. 0 for Transformer-XL, 1 for Shaw et al, 2 for Vaswani et al, 3 for Al Rfou et al.
sample_softmax (:obj:`int`, optional, defaults to -1):
number of samples in sampled softmax
adaptive (:obj:`boolean`, optional, defaults to :obj:`True`):
use adaptive softmax
dropout (:obj:`float`, optional, defaults to 0.1):
The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
dropatt (:obj:`float`, optional, defaults to 0):
The dropout ratio for the attention probabilities.
untie_r (:obj:`boolean`, optional, defaults to :obj:`True`):
Untie relative position biases
init (:obj:`string`, optional, defaults to `normal`):
Parameter initializer to use
init_range (:obj:`float`, optional, defaults to 0.01):
Parameters initialized by U(-init_range, init_range).
proj_init_std (:obj:`float`, optional, defaults to 0.01):
Parameters initialized by N(0, init_std)
init_std (:obj:`float`, optional, defaults to 0.02):
Parameters initialized by N(0, init_std)
layer_norm_epsilon (:obj:`float`, optional, defaults to 1e-5):
The epsilon to use in the layer normalization layers
Example::
>>> from transformers import TransfoXLConfig, TransfoXLModel
>>> # Initializing a Transformer XL configuration
>>> configuration = TransfoXLConfig()
>>> # Initializing a model from the configuration
>>> model = TransfoXLModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "transfo-xl"
......
src/transformers/configuration_utils.py
View file @ a75c64d8
This diff is collapsed.
src/transformers/configuration_xlm.py
View file @ a75c64d8
This diff is collapsed.
src/transformers/configuration_xlnet.py
View file @ a75c64d8
This diff is collapsed.
src/transformers/convert_dialogpt_original_pytorch_checkpoint_to_pytorch.py
View file @ a75c64d8
......@@ -27,5 +27,6 @@ if __name__ == "__main__":
checkpoint_path = os.path.join(args.dialogpt_path, f"{MODEL}_ft.pkl")
pytorch_dump_folder_path = f"./DialoGPT-{MODEL}"
convert_dialogpt_checkpoint(
checkpoint_path, pytorch_dump_folder_path,
checkpoint_path,
pytorch_dump_folder_path,
)
src/transformers/convert_graph_to_onnx.py
View file @ a75c64d8
......@@ -38,24 +38,39 @@ class OnnxConverterArgumentParser(ArgumentParser):
super().__init__("ONNX Converter")
self.add_argument(
"--pipeline", type=str, choices=SUPPORTED_PIPELINES, default="feature-extraction",
"--pipeline",
type=str,
choices=SUPPORTED_PIPELINES,
default="feature-extraction",
)
self.add_argument(
"--model", type=str, required=True, help="Model's id or path (ex: bert-base-cased)",
"--model",
type=str,
required=True,
help="Model's id or path (ex: bert-base-cased)",
)
self.add_argument("--tokenizer", type=str, help="Tokenizer's id or path (ex: bert-base-cased)")
self.add_argument(
"--framework", type=str, choices=["pt", "tf"], help="Framework for loading the model",
"--framework",
type=str,
choices=["pt", "tf"],
help="Framework for loading the model",
)
self.add_argument("--opset", type=int, default=11, help="ONNX opset to use")
self.add_argument(
"--check-loading", action="store_true", help="Check ONNX is able to load the model",
"--check-loading",
action="store_true",
help="Check ONNX is able to load the model",
)
self.add_argument(
"--use-external-format", action="store_true", help="Allow exporting model >= than 2Gb",
"--use-external-format",
action="store_true",
help="Allow exporting model >= than 2Gb",
)
self.add_argument(
"--quantize", action="store_true", help="Quantize the neural network to be run with int8",
"--quantize",
action="store_true",
help="Quantize the neural network to be run with int8",
)
self.add_argument("output")
......@@ -376,7 +391,10 @@ def quantize(onnx_model_path: Path) -> Path:
)
quantized_model = quantize(
model=onnx_model, quantization_mode=QuantizationMode.IntegerOps, force_fusions=True, symmetric_weight=True,
model=onnx_model,
quantization_mode=QuantizationMode.IntegerOps,
force_fusions=True,
symmetric_weight=True,
)
# Append "-quantized" at the end of the model's name
......
src/transformers/convert_marian_to_pytorch.py
View file @ a75c64d8
......@@ -255,7 +255,11 @@ license: apache-2.0
def write_model_card(
hf_model_name: str, repo_root="OPUS-MT-train", save_dir=Path("marian_converted"), dry_run=False, extra_metadata={},
hf_model_name: str,
repo_root="OPUS-MT-train",
save_dir=Path("marian_converted"),
dry_run=False,
extra_metadata={},
) -> str:
"""Copy the most recent model's readme section from opus, and add metadata.
upload command: aws s3 sync model_card_dir s3://models.huggingface.co/bert/Helsinki-NLP/ --dryrun
......@@ -604,7 +608,9 @@ class OpusState:
assert "hidden_size" not in cfg.to_dict()
load_layers_(
model.model.encoder.layers, state_dict, BART_CONVERTER,
model.model.encoder.layers,
state_dict,
BART_CONVERTER,
)
load_layers_(model.model.decoder.layers, state_dict, BART_CONVERTER, is_decoder=True)
......
src/transformers/convert_reformer_trax_checkpoint_to_pytorch.py
View file @ a75c64d8
......@@ -49,10 +49,12 @@ def set_layer_weights_in_torch_lsh(weights, torch_layer, hidden_size):
torch.tensor(np_query_key).transpose(1, 2).contiguous().view(-1, hidden_size),
)
set_param(
torch_layer.self_attention.value, torch.tensor(np_value).transpose(1, 2).contiguous().view(-1, hidden_size),
torch_layer.self_attention.value,
torch.tensor(np_value).transpose(1, 2).contiguous().view(-1, hidden_size),
)
set_param(
torch_layer.output.dense, torch.tensor(np_dense).view(-1, hidden_size).contiguous().transpose(0, 1),
torch_layer.output.dense,
torch.tensor(np_dense).view(-1, hidden_size).contiguous().transpose(0, 1),
)
......@@ -64,16 +66,20 @@ def set_layer_weights_in_torch_local(weights, torch_layer, hidden_size):
np_dense = np.asarray(weights[3])
set_param(
torch_layer.self_attention.query, torch.tensor(np_query).transpose(1, 2).contiguous().view(-1, hidden_size),
torch_layer.self_attention.query,
torch.tensor(np_query).transpose(1, 2).contiguous().view(-1, hidden_size),
)
set_param(
torch_layer.self_attention.key, torch.tensor(np_key).transpose(1, 2).contiguous().view(-1, hidden_size),
torch_layer.self_attention.key,
torch.tensor(np_key).transpose(1, 2).contiguous().view(-1, hidden_size),
)
set_param(
torch_layer.self_attention.value, torch.tensor(np_value).transpose(1, 2).contiguous().view(-1, hidden_size),
torch_layer.self_attention.value,
torch.tensor(np_value).transpose(1, 2).contiguous().view(-1, hidden_size),
)
set_param(
torch_layer.output.dense, torch.tensor(np_dense).view(-1, hidden_size).contiguous().transpose(0, 1),
torch_layer.output.dense,
torch.tensor(np_dense).view(-1, hidden_size).contiguous().transpose(0, 1),
)
......@@ -83,7 +89,9 @@ def set_block_weights_in_torch(weights, torch_block, hidden_size):
layer_norm_1_weight = np.asarray(layer_norm_1[0])
layer_norm_1_bias = np.asarray(layer_norm_1[1])
set_param(
torch_block.attention.layer_norm, torch.tensor(layer_norm_1_weight), torch.tensor(layer_norm_1_bias),
torch_block.attention.layer_norm,
torch.tensor(layer_norm_1_weight),
torch.tensor(layer_norm_1_bias),
)
# lsh weights + output
......@@ -104,7 +112,9 @@ def set_block_weights_in_torch(weights, torch_block, hidden_size):
layer_norm_2_weight = np.asarray(intermediate_weights[0][0])
layer_norm_2_bias = np.asarray(intermediate_weights[0][1])
set_param(
torch_block.feed_forward.layer_norm, torch.tensor(layer_norm_2_weight), torch.tensor(layer_norm_2_bias),
torch_block.feed_forward.layer_norm,
torch.tensor(layer_norm_2_weight),
torch.tensor(layer_norm_2_bias),
)
# intermediate dense
......@@ -133,7 +143,8 @@ def set_model_weights_in_torch(weights, torch_model, hidden_size):
# word embeds
word_embeddings = np.asarray(weights[1])
set_param(
torch_model_reformer.embeddings.word_embeddings, torch.tensor(word_embeddings),
torch_model_reformer.embeddings.word_embeddings,
torch.tensor(word_embeddings),
)
if isinstance(weights[3], tuple):
......
src/transformers/data/datasets/glue.py
View file @ a75c64d8
This diff is collapsed.
src/transformers/data/datasets/squad.py
View file @ a75c64d8
This diff is collapsed.
src/transformers/data/processors/glue.py
View file @ a75c64d8
This diff is collapsed.
src/transformers/data/processors/utils.py
View file @ a75c64d8
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment